HPM: A Hybrid Model for User’s Behavior Prediction Based on N-Gram Parsing and Access Logs

Algorithm 1

Weight generator.

	Input: access logs (AL)
	Output: Weighted N-grams stored in weighted logs (WL) of order m × n
	Begin
(1)	Read (AL);
(2)	PL ← Preprocess (AL);//PL = Processed Logs
(3)	NC-graph ← BipartiteGraphGen (PL); //NC-graph = N-gram associated click-graph
(4)	WL ← WeightCalculator (NC-graph); //is weighted logs stored in form of m × n weight matrix
(5)	Return (WL);
	End